Virtual driving-based tunnel visual guidance system evaluation method

Abstract

This invention discloses an evaluation method for tunnel visual guidance systems based on virtual driving, belonging to the field of traffic information technology. It addresses the problem that current evaluation methods for tunnel visual guidance elements do not consider the comprehensive elements of the tunnel visual guidance system and fail to conform to the dynamic visual characteristics of drivers. The invention includes: obtaining visual guidance data from a real tunnel; constructing a digital twin scene of the tunnel visual guidance system based on this data; building a virtual driving experimental environment based on the driver's perspective; obtaining evaluation indicators for virtual driving; constructing an evaluation indicator system based on the evaluation indicators; and completing the evaluation of the tunnel visual guidance system based on the digital twin scene, the virtual driving experimental environment, and the evaluation indicator system. This invention considers a combination of quantitative and qualitative evaluation indicators in its tunnel visual guidance system evaluation method and conforms to the dynamic visual characteristics of drivers, thus improving the scientific rigor and accuracy of the tunnel visual guidance system evaluation.

Description

Technical Field

[0001] This invention relates to the field of traffic information technology, and in particular to an evaluation method for tunnel visual guidance systems based on virtual driving. Background Technology

[0002] Vision is the primary channel for drivers to obtain driving information, and the rationality of the visual guidance system setting in tunnel scenarios is related to ensuring smooth traffic flow and driving safety.

[0003] Currently, the evaluation of visual guidance elements within tunnels typically uses indicators such as average road surface brightness and road surface brightness uniformity, which are required by tunnel lighting standards. This only assesses the effectiveness of lighting fixtures within the tunnel and cannot provide an evaluation method that aligns with the dynamic visual characteristics of drivers. Existing technologies lack a human-centered evaluation method and tool for visual guidance elements within tunnels that considers all aspects of the tunnel visual guidance system. Summary of the Invention

[0004] The purpose of this invention is to provide an evaluation method for tunnel visual guidance systems based on virtual driving, which solves the problem that existing tunnel visual guidance systems are only based on tunnel lighting specifications and can only evaluate the lighting effect of lamps in the tunnel, without considering the comprehensive elements of visual guidance in the tunnel and the dynamic visual characteristics of the driver.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] This invention provides an evaluation method for a tunnel vision guidance system based on virtual driving, comprising:

[0007] Obtain visual guidance data of the actual tunnel; the visual guidance data includes panoramic video data of the tunnel or video data from the driving perspective.

[0008] A digital twin scene of the tunnel visual guidance system of the real tunnel is constructed based on the visual guidance data;

[0009] Build a virtual driving test environment based on the driver's perspective;

[0010] The evaluation indicators for virtual driving are obtained; the evaluation indicators include qualitative evaluation indicators and quantitative evaluation indicators; the quantitative evaluation indicators include: minimum stopping sight distance, average road surface brightness, road surface brightness uniformity, and light environment comfort; the qualitative evaluation indicators include: road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, traffic guidance effectiveness, and mitigation of the black hole effect;

[0011] Construct an evaluation index system based on the aforementioned evaluation indicators;

[0012] The tunnel visual guidance system is evaluated based on the digital twin scenario, the virtual driving experimental environment, and the evaluation index system.

[0013] Compared with existing technologies, this invention provides an evaluation method for tunnel visual guidance systems based on virtual driving. It obtains visual guidance data from a real tunnel, constructs a digital twin scene of the tunnel visual guidance system based on this data, and builds a virtual driving experimental environment based on the driver's perspective. Qualitative evaluation indicators for virtual driving are obtained: road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, traffic guidance effectiveness, and mitigation of the black-and-white hole effect. Quantitative evaluation indicators for virtual driving are also obtained: minimum stopping sight distance, average road surface brightness, road surface brightness uniformity, and light environment comfort. These evaluation indicators cover all elements related to visual guidance within the tunnel. The driver drives in the digital twin scene and virtual driving experimental environment from a first-person perspective. The evaluation indicator system, encompassing both quantitative and qualitative evaluation indicators, calculates the corresponding evaluation indicator results for each indicator during the driving process. This method considers the comprehensive elements of visual guidance within the tunnel and uses the driver's perspective as the first-person perspective, conforming to the driver's dynamic visual characteristics. Furthermore, the final evaluation result is obtained by weighting and summing the results of each evaluation indicator, thus completing the evaluation of the tunnel visual guidance system and greatly improving the scientific rigor and accuracy of the evaluation. Attached Figure Description

[0014] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0015] Figure 1 The flowchart of the evaluation method for a tunnel visual guidance system based on virtual driving provided by the present invention;

[0016] Figure 2 A classification diagram of evaluation indicators for the tunnel visual guidance system based on virtual driving provided by this invention;

[0017] Figure 3 This is a reference value diagram for the minimum stopping sight distance in tunnels provided by the present invention;

[0018] Figure 4 This invention provides a reference value diagram of the average brightness of the road surface in the middle section of the tunnel.

[0019] Figure 5 This invention provides a reference value diagram for the overall uniformity of tunnel pavement brightness.

[0020] Figure 6 The diagram shows the reference values ​​for the overall uniformity of tunnel pavement brightness provided by this invention. Detailed Implementation

[0021] To facilitate a clear description of the technical solutions in the embodiments of the present invention, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and effect. For example, the first threshold and the second threshold are merely used to distinguish different thresholds and do not limit their order. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that the terms "first" and "second" are not necessarily different.

[0022] It should be noted that in this invention, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0023] In this invention, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, a combination of a and b, a combination of a and c, a combination of b and c, or a, b, and c, where a, b, and c can be single or multiple.

[0024] The technical solution of this application will now be described in conjunction with the accompanying drawings:

[0025] Figure 1 The flowchart of the evaluation method for a tunnel vision guidance system based on virtual driving provided by the present invention includes the following steps:

[0026] Step 101: Obtain visual guidance data of the actual tunnel; the visual guidance data includes panoramic video data of the tunnel or video data from the driving perspective.

[0027] Among them, visual guidance data represents all elements seen visually, such as traffic lights, obstacles, etc.

[0028] A panoramic video of driving through a tunnel is a 360-degree video shot using a 3D camera while driving through a tunnel, while a driving perspective video is a video shot from the driver's first-person perspective.

[0029] Step 102: Construct a digital twin scene of the tunnel visual guidance system of the real tunnel based on the visual guidance data.

[0030] Digital twins are digital representations of actual physical products. During the design and production process, parameters from the simulation analysis model are transmitted to the product's defined 3D geometric model, then to a digital production line where the product is manufactured into a real physical product. This process is then reflected in the product's defined 3D geometric model through an online digital inspection / measurement system, and finally fed back into the simulation analysis model. By integrating the entire lifecycle model through digital links, and seamlessly integrating and synchronizing it with actual intelligent manufacturing systems, digital measurement and inspection systems, and embedded cyber-physical systems, the digital twin scenario allows for visualization of potential situations in the actual physical application scenario, enabling dynamic and real-time evaluation of the system's functionality and performance. A digital twin scenario applies digital twin technology to a physical scenario, enabling the reconstruction and analysis of the physical scene.

[0031] This invention is based on data collected from real tunnels. It uses modeling tools to construct a twin scene of the tunnel visual guidance system corresponding to the real tunnel, and reproduces the visual guidance elements in the real tunnel in the virtual scene.

[0032] Step 103: Build a virtual driving test environment based on the driver's perspective.

[0033] Virtual driving refers to a driving experience that allows users to feel the visual, auditory, and tactile sensations of a car in a virtual driving environment, also known as car driving simulation or car driving simulator.

[0034] Virtual driving test environments simulate real driving environments. The simulated objects include all objects that the driver can perceive during driving, such as traffic lights, lane indicators, and obstacles.

[0035] Step 104: Obtain evaluation indicators for virtual driving; the evaluation indicators include qualitative evaluation indicators and quantitative evaluation indicators; the quantitative evaluation indicators include: minimum stopping sight distance, average road surface brightness, road surface brightness uniformity, and light environment comfort; the qualitative evaluation indicators include: road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, traffic guidance effectiveness, and mitigation of the black hole effect.

[0036] Among them, minimum stopping sight distance is the shortest distance required for a driver to stop before spotting an obstacle;

[0037] The average luminance of the road surface is the average value of the luminance of each point measured or calculated at a pre-set point on the road surface in accordance with the relevant regulations of the International Commission on Illumination (CIE).

[0038] Road surface brightness uniformity refers to the ratio of the minimum brightness to the average brightness on the tunnel road surface;

[0039] Light environment comfort refers to the degree of comfort felt in a visual space where light is present.

[0040] Road marking visibility, luminous sign visibility, and reflective sign visibility refer to the degree to which drivers can recognize and distinguish road markings, luminous signs, and reflective signs.

[0041] Glare refers to the degree of visual discomfort caused by an unsuitable distribution of brightness in the field of vision or extreme brightness contrast in space and time.

[0042] Traffic guidance effectiveness refers to the degree of effectiveness of traffic guidance facilities.

[0043] In the mitigation of the black hole and white hole effects, the black hole effect refers to the phenomenon where, when entering a tunnel, the light suddenly changes from bright to dark, causing the pupils to constrict rapidly, and the human eye sees only darkness; the white hole effect refers to the phenomenon where, when exiting a tunnel, the light suddenly changes from dark to bright, causing the pupils to constrict rapidly, and the human eye sees only white light; the mitigation degree of the black hole and white hole effects refers to the extent to which the tunnel design mitigates the black hole and white hole effects.

[0044] Step 105: Construct an evaluation index system based on the evaluation indexes.

[0045] The evaluation index system is used to calculate and output the results of each evaluation index and the target evaluation results.

[0046] Step 106: Evaluate the tunnel visual guidance system based on the digital twin scenario, the virtual driving experimental environment, and the evaluation index system.

[0047] Based on the digital twin scenario and virtual driving test environment, simulate all situations of driving in a real tunnel. During the simulated driving process, calculate the results of each evaluation index according to the evaluation index system to obtain the target evaluation result of the tunnel visual guidance system and complete the evaluation of the tunnel visual guidance system.

[0048] As an optional implementation, obtaining the visual guidance data of the real tunnel includes:

[0049] The system employs video data acquisition equipment to travel at a set speed along the designated lane lines of the tunnel and collect panoramic video data or driving-view video data; the video data acquisition equipment includes at least a panoramic camera and a driving recorder.

[0050] Alternatively, video data acquisition equipment can be used to sample tunnel panoramic video data or driving perspective video data at different speeds within a set speed range multiple times.

[0051] Among them, the acquisition equipment includes panoramic cameras, dashcams, etc. Using the acquisition equipment, the vehicle is driven at a certain speed along a certain lane and the panoramic video data or driving perspective video data of the tunnel is collected; or the panoramic video data or driving perspective video data of the tunnel corresponding to different speeds is obtained by sampling multiple times at different speeds within the tunnel speed range, and the panoramic video data or driving perspective video data of the tunnel can be directly used for the evaluation experiment of the tunnel visual guidance system.

[0052] As an optional implementation method, the construction of the virtual driving test environment based on the driver's perspective includes:

[0053] Construct a driving data acquisition system; the driving data acquisition system includes a driving simulator, a virtual reality helmet, an emotion monitoring terminal, an eye tracker, and computer equipment;

[0054] The driving simulator is used to provide users with driving interaction peripherals, conduct dynamic visual scene experiments, and output driving behavior data of the driver during the experiment.

[0055] The virtual reality helmet is used to provide drivers with an immersive tunnel driving environment;

[0056] The emotion monitoring terminal includes a wristband-type emotion monitoring terminal, used to monitor the driver's physiological data during the experiment, and to analyze and optimize the driver's qualitative index evaluation results based on the physiological data; the physiological data includes at least the driver's electrocardiogram, skin resistivity, heart rate, and electromyography during the experiment.

[0057] The eye tracker is used to monitor eye movement data during the driver's experiment, and to analyze and optimize the driver's qualitative evaluation results based on the eye movement data; the eye movement data is used to represent changes in the driver's attention during the experiment.

[0058] The driving data acquisition system is used to build a virtual driving test environment from the driver's first-person perspective.

[0059] Among them, a virtual driving experimental environment from the driver's first-person perspective is built by using hardware devices such as driving simulators, virtual reality helmets, emotion monitoring terminals, eye trackers and computers to provide the driver's dynamic visual characteristics.

[0060] Among them, the driving simulator provides experimental personnel with driving interaction peripherals to conduct scene experiments of driver dynamic vision, and supports the output of driving behavior data such as steering wheel steering, acceleration, deceleration, and braking. The driving simulator's window display allows experimental personnel to conduct evaluation experiments without wearing a helmet.

[0061] Virtual reality headsets provide experimenters with an immersive tunnel driving experimental environment and can be used in conjunction with driving simulators to replace window displays;

[0062] The emotion monitoring terminal monitors physiological data such as electrocardiogram, skin resistance, heart rate, and electromyography of drivers during the experiment by equipping experimental personnel with a wristband-type emotion monitoring terminal. This data is used to analyze and optimize the qualitative evaluation results of the experimental personnel.

[0063] Eye trackers are used to monitor changes in the attention of experimenters and to verify and optimize qualitative evaluation results such as the recognizability of signs and markings.

[0064] As an optional implementation, the evaluation index system is used for:

[0065] Obtain the evaluation index result range; the evaluation index result range includes the standard value range and full score of the quantitative evaluation index result range and the score range of the qualitative evaluation index result range;

[0066] Calculate the results of the quantitative evaluation index; during the virtual tunnel driving process, match the corresponding quantitative evaluation index and perform quantitative calculations to obtain numerical results;

[0067] If the numerical result falls within the standard value range, the quantitative evaluation index result is full marks; if the numerical result falls outside the standard value range, the quantitative evaluation index result is zero marks.

[0068] Calculate the scores corresponding to the qualitative evaluation index results.

[0069] For example, each evaluation indicator has a maximum score of 10 points, with a value range of [0, 10]. Quantitative evaluation indicators include minimum stopping sight distance, average road surface brightness, road surface brightness uniformity, and light environment comfort. Numerical results are obtained through quantitative calculations, and then compared with the value range. If the numerical result falls within the range, the indicator receives full marks; if the numerical result falls outside the range, the indicator receives zero marks. Qualitative evaluation indicators include road marking visibility, electro-optical sign visibility, reflective sign visibility, glare, traffic guidance effectiveness, and mitigation of the black hole effect. These are obtained by conducting a questionnaire survey of the experimental personnel after the experiment, converting qualitative results into quantitative scores.

[0070] The evaluation indicators for tunnel visual guidance systems combine quantitative and qualitative methods, including 10 indicators: minimum stopping sight distance, average road surface brightness, road surface brightness uniformity, light environment comfort, road marking recognition, electro-optical sign recognition, reflective sign recognition, glare intensity, traffic guidance effectiveness, and mitigation of the black hole effect, covering all elements related to visual guidance within tunnels.

[0071] Furthermore, the 10 indicators cover objects such as lighting fixtures, road markings, reflective signs, electro-optical signs, variable message signs, variable speed limit signs, lane indicators, and traffic lights, encompassing all objects related to visual guidance within the tunnel.

[0072] As an optional implementation, the evaluation of the tunnel visual guidance system based on the digital twin scenario, the virtual driving experimental environment, and the evaluation index system includes:

[0073] According to the experimental conditions, virtual tunnel driving was conducted in a virtual tunnel driving scenario; the virtual tunnel driving scenario included the digital twin scenario and the virtual driving experimental environment; the experimental conditions included different vehicle types, driver ages, and driver experience.

[0074] The evaluation index results are calculated during the virtual tunnel driving process according to the evaluation index system.

[0075] The weights of each evaluation index in the evaluation index system are obtained based on the analytic hierarchy process (AHP). The results of each evaluation index are weighted and then summed to obtain the final evaluation result. The evaluation of the tunnel visual guidance system is completed based on the final evaluation result.

[0076] This method involves selecting different vehicle types, driver ages, and driving experience to set experimental conditions. Repeated experiments under these conditions yield multiple single-test evaluation index results. The average of these multiple single-test evaluation indexes is then taken as the final evaluation index. For example, selecting drivers with over 5 years of driving experience and testing different vehicle models, three repeated glare intensity experiments are conducted for each model. The average of these three single-test glare intensity evaluation index results is then taken as the final glare intensity evaluation index. By conducting the same experiment under different conditions and using the average of the single-test results as the final evaluation index, the accuracy of the experimental results is greatly improved.

[0077] Furthermore, a weighted summation of all evaluation indicators yielded the final evaluation result of the visual guidance system for the experimental tunnel. The weights of the evaluation indicators were determined based on expert scoring using the analytic hierarchy process (AHP).

[0078] The formula for calculating the final evaluation result of a specific tunnel visual guidance system is as follows:

[0079]

[0080] In formula (1), V represents the final evaluation result, P represents the evaluation index, i represents the i-th evaluation index, and k represents the evaluation index. iLet V be the weight of the i-th evaluation index, V takes values ​​in the range [0, 100], k takes values ​​in the range (0, 10), and i takes values ​​in the range i = 1, 2, ..., 10.

[0081] like Figure 2 Specifically, the following parameters can be used: minimum stopping sight distance P1, average road surface brightness P2, road surface brightness uniformity P3, lighting environment comfort P4, road marking visibility P5, electro-optical sign visibility P6, reflective sign visibility P7, glare P8, traffic guidance effectiveness P9, and mitigation of the black hole effect P1. 10 .

[0082] Minimum stopping sight distance P1: This is a quantitative indicator used to assess whether the shortest driving distance required for a driver to safely stop in front of an obstacle in a tunnel environment meets driving requirements.

[0083] Average road surface brightness P2: This is a quantitative indicator used to evaluate whether the average brightness of the road surface inside the tunnel meets the driver's scene recognition requirements. The value is the average of the brightness of each point measured or calculated at a pre-set point on the road surface.

[0084] Road surface brightness uniformity P3: This is a quantitative indicator used to evaluate whether the illumination distribution of the road surface inside the tunnel is uniform. The value is the ratio of the minimum brightness measured or calculated at a pre-set point on the road surface to the average brightness.

[0085] Lighting comfort level P4: This is a quantitative indicator used to assess whether the overall lighting environment inside the tunnel falls within the driver's comfort range. It is determined by the average illuminance and color temperature of the road surface inside the tunnel.

[0086] Road marking recognition P5: This is a qualitative indicator used to assess whether road markings in tunnels meet the dynamic recognition needs of drivers.

[0087] Electro-optical sign recognition rate P6: This is a qualitative indicator used to evaluate whether the electro-optical signs in the tunnel meet the dynamic recognition needs of drivers.

[0088] Reflective sign visibility P7: This is a qualitative indicator used to evaluate whether reflective signs in tunnels meet the dynamic visibility needs of drivers, including daytime visibility and nighttime visibility.

[0089] Glare P8: A qualitative indicator used to assess whether there are unsuitable brightness distributions or ranges in the field of vision within a tunnel, or extreme contrasts that cause discomfort or reduce the ability to observe targets or details.

[0090] Traffic guidance effectiveness P9: This is a qualitative indicator used to evaluate the effectiveness of the installation of guidance facilities such as variable information signs, variable speed limit signs, delineators, lane indicators, traffic lights, and dynamic guidance signs in tunnels.

[0091] Mitigation of the black hole effect P 10 This is a qualitative indicator used to assess the degree of mitigation of the black hole and white hole effects when drivers enter and exit tunnels.

[0092] The formula for calculating the final evaluation result of the tunnel visual guidance system for different tunnels is as follows:

[0093]

[0094] In formula (2), j represents the experiment on the j-th tunnel, and l represents the l-th visual guidance system setting conditions given by the designer.

[0095] By conducting the same experiment under different experimental conditions, taking the average of the results of a single experiment as the final result, and then weighting and summing the results of each experiment to obtain the final result, the accuracy and scientific nature of the experiment are improved.

[0096] Simultaneously, based on the final evaluation results and process data, the data of different evaluation indicators are analyzed to identify problems such as: minimum parking sight distance not meeting the standard, low average road surface brightness, uneven road surface brightness, uncomfortable lighting environment, poor visibility of road signs and markings, light sources that cause glare, unclear traffic guidance indicators, and areas with excessively high contrast at tunnel entrances and exits. The tunnel visual guidance system is then analyzed, and corresponding optimization suggestions are given to complete the evaluation of the tunnel visual guidance system.

[0097] An evaluation tool for tunnel visual guidance systems based on the driver's first-person perspective has been developed. It not only supports driver driving and dynamic evolution experiments of visual guidance systems in tunnels, but also provides optimization suggestions for tunnels.

[0098] As an optional implementation, calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes:

[0099] When the evaluation metric is the minimum stopping sight distance, stable virtual driving is performed based on the speed limit range of the real tunnel corresponding to the virtual tunnel, using the upper speed limit within the speed limit range.

[0100] Randomly generate parking obstacles in the digital twin scenario;

[0101] Calculate the driving distance for a driver to safely stop in a virtual scene, where the driving distance is the distance from when the parking obstacle appears in the driver's field of vision to when the vehicle stops; determine the time when the parking obstacle appears in the driver's field of vision as the starting time, and calculate the driver's minimum stopping sight distance value based on the starting time;

[0102] Valid experimental data obtained from multiple experiments on the same driver are acquired. Based on the longitudinal slope value, speed limit value and minimum stopping sight distance value of the driving section in the valid experimental data, the results are compared with the minimum stopping sight distance table of the tunnel to determine the evaluation index result of the single minimum stopping sight distance.

[0103] The average of the single minimum parking sight distance evaluation index results output under different experimental conditions is taken as the minimum parking sight distance evaluation index result.

[0104] Specifically, the calculation steps for the minimum parking sight distance P1 are as follows:

[0105] (1) Select drivers with more than 5 years of driving experience for different vehicle models to conduct the experiment;

[0106] (2) Drivers use driving simulators to generate virtual driving perspectives of specified vehicle models and conduct tunnel driving experiments in digital twin scenarios. According to the maximum speed limit requirements of the tunnel, they select driving speeds of 40 km / h, 60 km / h, 80 km / h or 100 km / h for the experiment.

[0107] (3) Once the virtual driving reaches the maximum speed limit and stabilizes, parking obstacles are randomly generated in the digital twin scenario. The driver identifies the obstacles and immediately performs the parking operation.

[0108] (4) The system automatically calculates the driving distance from when the driver sees the obstacle ahead to when the vehicle safely stops in front of the obstacle in the virtual scene. The time when the obstacle is seen is taken as the starting time when the obstacle appears in the driver's field of vision, and the minimum stopping sight distance value of the driver is calculated.

[0109] (5) Five experiments are conducted by the same driver. The middle three valid experimental data are used to output the longitudinal slope, speed limit, and minimum stopping sight distance of the three experimental driving sections. Figure 3 As shown in the table of minimum stopping sight distances in tunnels, if all values ​​are greater than the minimum stopping sight distance requirement, the minimum stopping sight distance evaluation index is set to 10; otherwise, the value is 0.

[0110] (6) Drivers of different vehicle types repeat steps (2) to (5) respectively, and output the corresponding evaluation index results. If the index value of all types of drivers is 10, the result of this index is 10; otherwise, it is 0.

[0111] As an optional implementation, calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes:

[0112] When the evaluation index is the average brightness of the road surface and the uniformity of the road surface brightness, in the digital twin scenario, points at fixed intervals on the center line of the lane are taken as road surface test points, and the brightness value of each road surface test point is calculated.

[0113] Valid road surface test points are obtained based on the brightness value of each road surface test point. The average brightness value of the valid road surface test points is compared with the road lighting standard for highway tunnels to determine the average brightness evaluation index result of the road surface. The ratio of the minimum brightness value among the brightness values ​​of the valid road surface test points to the average brightness value of the valid road surface test points is compared with the road lighting standard for highway tunnels to determine the brightness uniformity evaluation index result of the road surface.

[0114] Specifically, the calculation steps for the average road surface brightness P2 are as follows:

[0115] (1) In the constructed digital twin scene, road test points at fixed intervals are selected sequentially according to the center line of the lane, and the brightness value of the point is calculated.

[0116] (2) The average brightness of all valid test points in the tunnel is taken as the result of the road surface average brightness calculation.

[0117] (3) Figure 4 As shown, according to the road lighting standards for highway tunnels, if the average road surface brightness is greater than the standard requirement, the average road surface brightness index is assigned 10; otherwise, it is 0.

[0118] The calculation steps for road surface brightness uniformity P3 are as follows:

[0119] (1) In the constructed digital twin scene, road test points at fixed intervals are selected sequentially according to the center line of the lane, and the brightness value of the point is calculated.

[0120] (2) The average brightness of all valid test points in the tunnel is taken as the result of the road surface average brightness calculation, and the ratio of the minimum brightness to the average brightness is the result of the road surface brightness uniformity calculation.

[0121] (3) Figure 5 As shown, according to the road lighting standard for highway tunnels, if the road surface brightness uniformity is greater than the standard requirement, the road surface brightness uniformity index is assigned 10; otherwise, it is 0.

[0122] As an optional implementation, calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes:

[0123] When the evaluation index is light environment comfort, in the digital twin scenario, points at fixed intervals on the center line of the lane are taken as road surface test points, and the illuminance and color temperature of each road surface test point are calculated.

[0124] Calculate the average illuminance and average color temperature at the road surface test points in the tunnel entrance section, transition section, middle section, and exit section; determine the light environment comfort evaluation index results for each section based on the lighting comfort relationship curve between lighting color temperature and illuminance;

[0125] The average of the results of each segment of the light environment comfort evaluation index is taken as the light environment comfort evaluation index result.

[0126] Specifically, the calculation steps for ambient light comfort level P4 are as follows:

[0127] (1) In the constructed digital twin scene, road test points with fixed intervals are selected sequentially according to the center line of the lane, and the illuminance and color temperature of the point are calculated.

[0128] (2) Calculate the average illuminance and average color temperature of each segment: entrance segment, transition segment, middle segment, and exit segment.

[0129] (3) Figure 6 As shown, based on (average illuminance, average color temperature), compare the lighting comfort relationship curve between lighting color temperature and illuminance proposed by the International Commission on Illumination (CIE). If the value falls within the "comfortable zone", the lighting environment comfort value for that segment is 10; otherwise, it is 0.

[0130] (4) The average value of the light environment comfort of the tunnel in this experiment was calculated for each segment.

[0131] As an optional implementation, calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes:

[0132] When the evaluation indicators are road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and mitigation of the black hole effect, stable virtual driving is performed based on the speed limit range of the real tunnel corresponding to the virtual tunnel, using the upper limit of the speed limit range.

[0133] In the digital twin scenario, experiments were conducted on the effectiveness of road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and mitigation of the black-and-white hole effect.

[0134] In the digital twin scenario, road marking objects, electro-optical sign objects, reflective sign objects, glare road sections, and black-and-white hole effect mitigation road sections are generated respectively. The evaluation results of single-time road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and black-and-white hole effect mitigation are determined based on driver scores.

[0135] The average value of the evaluation results of the single road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and black-and-white hole effect mitigation under different experimental conditions is taken as the evaluation result of the road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and black-and-white hole effect mitigation.

[0136] Specifically, the calculation steps for road marking visibility P5 are as follows:

[0137] (1) Select drivers with more than 5 years of driving experience for different vehicle types to conduct experiments. In the constructed digital twin scenario, set up experiments for the road marking recognition.

[0138] (2) Drivers use driving simulators to generate virtual driving perspectives of specified vehicle models and conduct tunnel driving experiments in digital twin scenarios. According to the maximum speed limit requirements of the tunnel, they select driving speeds of 40 km / h, 60 km / h, 80 km / h or 100 km / h for the experiment.

[0139] (3) Once the virtual driving reaches the maximum speed limit and stabilizes, the road marking object to be tested is generated in the digital twin scenario. After the driver passes through, the system automatically pops up a questionnaire.

[0140] (4) Set up a questionnaire for a certain type of line, with options including: very clear, relatively clear, clear, relatively unclear, unclear, not found, and values ​​of (10, 8, 6, 4, 2, 0) respectively. Take the average value of multiple experiments on the same subject.

[0141] (5) Repeat steps (2) to (4) for drivers of different vehicle types and take the average value as the evaluation index result of the corresponding evaluation index.

[0142] The calculation steps for the P6 distinguishability of the electro-optical sign are as follows:

[0143] (1) Select drivers with more than 5 years of driving experience in different vehicle models to conduct experiments. In the constructed digital twin scenario, set up experiments for the recognition of electro-optical signs.

[0144] (2) Drivers use driving simulators to generate virtual driving perspectives of specified vehicle models and conduct tunnel driving experiments in digital twin scenarios. According to the maximum speed limit requirements of the tunnel, they select driving speeds of 40 km / h, 60 km / h, 80 km / h or 100 km / h for the experiment.

[0145] (3) Once the virtual driving reaches the maximum speed limit and stabilizes, generate the electro-optical sign object to be tested in the digital twin scenario. After the driver passes through, the system will automatically pop up a questionnaire.

[0146] (4) Set up questionnaire content for a certain type of marker. The options include: very clear, relatively clear, clear, relatively unclear, unclear, not found, with values ​​of (10, 8, 6, 4, 2, 0) respectively. Take the average value of multiple experiments on the same subject.

[0147] (5) Repeat steps (2) to (4) for drivers of different vehicle types and take the average value as the evaluation index result of the corresponding evaluation index.

[0148] The calculation steps for reflective sign visibility P7 are as follows:

[0149] (1) Select drivers with more than 5 years of driving experience for different vehicle models to conduct experiments. In the constructed digital twin scenario, set up experiments for the recognizability of reflective signs.

[0150] (2) Drivers use driving simulators to generate virtual driving perspectives of specified vehicle models and conduct tunnel driving experiments in digital twin scenarios. According to the maximum speed limit requirements of the tunnel, they select driving speeds of 40 km / h, 60 km / h, 80 km / h or 100 km / h for the experiment.

[0151] (3) Once the virtual driving reaches the maximum speed limit and stabilizes, a reflective sign object to be tested is generated in the digital twin scene. After the driver passes through, the system automatically pops up a questionnaire.

[0152] (4) Set up questionnaire content for a certain type of marker. The options include: very clear, relatively clear, clear, relatively unclear, unclear, not found, with values ​​of (10, 8, 6, 4, 2, 0) respectively. Take the average value of multiple experiments on the same subject.

[0153] (5) Repeat steps (2) to (4) for drivers of different vehicle types and take the average value of the evaluation index results corresponding to the evaluation index.

[0154] The steps for calculating glare intensity P8 are as follows:

[0155] (1) Select drivers with more than 5 years of driving experience in different vehicle types to conduct experiments. In the constructed digital twin scenario, set up experiments for road sections that may produce glare.

[0156] (2) Drivers use driving simulators to generate virtual driving perspectives of specified vehicle models and conduct tunnel driving experiments in digital twin scenarios. According to the maximum speed limit requirements of the tunnel, they select driving speeds of 40 km / h, 60 km / h, 80 km / h or 100 km / h for the experiment.

[0157] (3) After the virtual driving reaches the maximum speed limit and stabilizes, the vehicle passes through the test section. After the driver passes through the test section, the system automatically pops up a questionnaire.

[0158] (4) Set up a questionnaire for this road section. The options include: no glare, barely feel glare, acceptable glare, glare threshold, uncomfortable glare, and intolerable glare. The values ​​are (10, 8, 6, 4, 2, 0) respectively. The average value is taken from multiple experiments on the same subject.

[0159] (5) Repeat steps (2) to (4) for drivers of different vehicle types and take the average value as the evaluation index result of the corresponding evaluation index.

[0160] Mitigation of the black hole effect P 10 The calculation steps are as follows:

[0161] (1) Select drivers with more than 5 years of driving experience for different vehicle types to conduct experiments. In the constructed digital twin scenario, set up experiments for the exit section and the entrance section respectively.

[0162] (2) Drivers use driving simulators to generate virtual driving perspectives of specified vehicle models and conduct tunnel driving experiments in digital twin scenarios. According to the maximum speed limit requirements of the tunnel, they select driving speeds of 40 km / h, 60 km / h, 80 km / h or 100 km / h for the experiment.

[0163] (3) After the virtual driving reaches the maximum speed limit and stabilizes, the vehicle passes through the test section. After the driver passes through the test section, the system automatically pops up a questionnaire.

[0164] (4) Set up a questionnaire for this road section. The options include: no difference, slight difference, obvious difference, difficult to identify, very difficult to identify, and completely unclear. The values ​​are (10, 8, 6, 4, 2, 0). The average value is taken from multiple experiments on the same subject.

[0165] (5) Repeat steps (2) to (4) for drivers of different vehicle types and take the average value as the evaluation index of the mitigation of the black hole effect.

[0166] As an optional implementation, calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes:

[0167] When the evaluation index is the effectiveness of traffic guidance, stable virtual driving is performed based on the speed limit range of the real tunnel corresponding to the virtual tunnel, using the upper speed limit within the speed limit range.

[0168] In the digital twin scenario, traffic guidance facilities, including at least variable information signs, variable speed limit signs, delineators, lane indicators, traffic lights, and dynamic guide signs, are randomly generated; the effectiveness evaluation index results for a single traffic guidance session are determined based on driver ratings.

[0169] The mean of the single traffic guidance effectiveness evaluation index results output under different experimental conditions is taken as the traffic guidance effectiveness evaluation index result.

[0170] Specifically, the calculation steps for traffic guidance effectiveness (P9) are as follows:

[0171] (1) Select drivers with more than 5 years of driving experience in different vehicle types to conduct experiments. In the constructed digital twin scenario, experiments were set up for guidance facilities such as variable information signs, variable speed limit signs, delineators, lane indicators, traffic lights, and dynamic guidance signs.

[0172] (2) Drivers use driving simulators to generate virtual driving perspectives of specified vehicle models and conduct tunnel driving experiments in digital twin scenarios. According to the maximum speed limit requirements of the tunnel, they select driving speeds of 40 km / h, 60 km / h, 80 km / h or 100 km / h for the experiment.

[0173] (3) After the virtual driving reaches the maximum speed limit and stabilizes, the vehicle passes through the test section. After the driver passes through the test section, the system automatically pops up a questionnaire.

[0174] (4) Set up questionnaire content for this road section. The options include: very clear, relatively clear, clear, relatively unclear, unclear, content or sign rephrased incorrectly or not seen. The values ​​are (10, 8, 6, 4, 2, 0) respectively. The average value is taken from multiple experiments on the same subject.

[0175] (5) Repeat steps (2) to (4) for drivers of different vehicle types and take the average value as the result of the traffic guidance effectiveness evaluation index.

[0176] Although the invention has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made therein without departing from the spirit and scope of the invention. Accordingly, this specification and drawings are merely exemplary descriptions of the invention as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its spirit and scope. Thus, if such modifications and modifications of the invention fall within the scope of the claims and their equivalents, the invention is also intended to include such modifications and modifications.

Claims

1. An evaluation method for a tunnel visual guidance system based on virtual driving, characterized in that, include: Obtain visual guidance data from real tunnels; The visual guidance data includes panoramic video data of the tunnel or video data from the driving perspective. A digital twin scene of the tunnel visual guidance system of the real tunnel is constructed based on the visual guidance data; Build a virtual driving test environment based on the driver's perspective; The evaluation indicators for virtual driving are obtained; the evaluation indicators include qualitative evaluation indicators and quantitative evaluation indicators. The quantitative evaluation indicators include: minimum stopping sight distance, average road surface brightness, road surface brightness uniformity, and light environment comfort; the qualitative evaluation indicators include: road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, traffic guidance effectiveness, and mitigation of the black hole effect. Construct an evaluation index system based on the aforementioned evaluation indicators; The evaluation of the tunnel visual guidance system is completed based on the digital twin scenario, the virtual driving experimental environment, and the evaluation index system. The visual guidance data for obtaining a real tunnel includes: The system employs video data acquisition equipment to travel at a set speed along the designated lane lines of the tunnel and collect panoramic video data or driving-view video data; the video data acquisition equipment includes at least a panoramic camera and a driving recorder. Alternatively, video data acquisition equipment can be used to sample tunnel panoramic video data or driving perspective video data at different speeds within a set speed range multiple times. The construction of the virtual driving test environment based on the driver's perspective includes: Construct a driving data acquisition system; the driving data acquisition system includes a driving simulator, a virtual reality helmet, an emotion monitoring terminal, an eye tracker, and computer equipment; The driving simulator is used to provide users with driving interaction peripherals, conduct dynamic visual scene experiments, and output driving behavior data of the driver during the experiment. The virtual reality helmet is used to provide drivers with an immersive tunnel driving environment; The emotion monitoring terminal includes a wristband-type emotion monitoring terminal, used to monitor the driver's physiological data during the experiment, and to analyze and optimize the driver's qualitative index evaluation results based on the physiological data; the physiological data includes at least the driver's electrocardiogram, skin resistivity, heart rate, and electromyography during the experiment. The eye tracker is used to monitor eye movement data during the driver's experiment, and to analyze and optimize the driver's qualitative evaluation results based on the eye movement data; the eye movement data is used to represent changes in the driver's attention during the experiment. The driving data acquisition system is used to build the virtual driving test environment from the driver's first-person perspective; The method further includes: When the evaluation index is light environment comfort, in the digital twin scenario, points at fixed intervals on the center line of the lane are taken as road surface test points, and the illuminance and color temperature of each road surface test point are calculated. Calculate the average illuminance and average color temperature at the road surface test points in the tunnel entrance section, transition section, middle section, and exit section; Based on the lighting comfort relationship curve between lighting color temperature and illuminance, the results of the lighting environment comfort evaluation index for each segment are determined; The average of the results of each segment of the light environment comfort evaluation index is taken as the light environment comfort evaluation index result.

2. The evaluation method for a tunnel visual guidance system based on virtual driving according to claim 1, characterized in that, The evaluation index system is used for: Obtain the evaluation index result range; the evaluation index result range includes the standard value range and full score of the quantitative evaluation index result range and the score range of the qualitative evaluation index result range; Calculate the results of the quantitative evaluation indicators; during virtual tunnel driving, match the corresponding quantitative evaluation indicators and perform quantitative calculations to obtain numerical results; If the numerical result falls within the standard value range, then the quantitative evaluation index result is full marks; If the numerical result falls outside the standard value range, the quantitative evaluation index result is zero. Calculate the scores corresponding to the qualitative evaluation index results.

3. The evaluation method for a tunnel visual guidance system based on virtual driving according to claim 2, characterized in that, The evaluation of the tunnel visual guidance system based on the digital twin scenario, the virtual driving experimental environment, and the evaluation index system includes: According to the experimental conditions, virtual tunnel driving was conducted in a virtual tunnel driving scenario; the virtual tunnel driving scenario included the digital twin scenario and the virtual driving experimental environment; the experimental conditions included different vehicle types, driver ages, and driver experience. The evaluation index results are calculated during the virtual tunnel driving process according to the evaluation index system. The weights of each evaluation index in the evaluation index system are obtained based on the analytic hierarchy process (AHP). The results of each evaluation index are weighted and then summed to obtain the final evaluation result. The evaluation of the tunnel visual guidance system is completed based on the final evaluation result.

4. The evaluation method for a tunnel visual guidance system based on virtual driving according to claim 3, characterized in that, The step of calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes: When the evaluation metric is the minimum stopping sight distance, stable virtual driving is performed based on the speed limit range of the real tunnel corresponding to the virtual tunnel, using the upper speed limit within the speed limit range. Randomly generate parking obstacles in the digital twin scenario; Calculate the driving distance for a driver to safely stop in a virtual scene, where the driving distance is the distance from when the parking obstacle appears in the driver's field of vision to when the vehicle stops; determine the time when the parking obstacle appears in the driver's field of vision as the starting time, and calculate the driver's minimum stopping sight distance value based on the starting time; Valid experimental data obtained from multiple experiments on the same driver are acquired. Based on the longitudinal slope value, speed limit value and minimum stopping sight distance value of the driving section in the valid experimental data, the results are compared with the minimum stopping sight distance table of the tunnel to determine the evaluation index result of the single minimum stopping sight distance. The average of the single minimum parking sight distance evaluation index results output under different experimental conditions is taken as the minimum parking sight distance evaluation index result.

5. The evaluation method for a tunnel visual guidance system based on virtual driving according to claim 4, characterized in that, The step of calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes: When the evaluation index is the average brightness of the road surface and the uniformity of the road surface brightness, in the digital twin scenario, points at fixed intervals on the center line of the lane are taken as road surface test points, and the brightness value of each road surface test point is calculated. Valid road surface test points are obtained based on the brightness value of each road surface test point. The average brightness value of the valid road surface test points is compared with the road lighting standard for highway tunnels to determine the average brightness evaluation index result of the road surface. The road surface brightness uniformity evaluation index result is determined by comparing the ratio of the minimum brightness value to the mean brightness value among the effective road surface test points with the road lighting standard for highway tunnels.

6. The evaluation method for a tunnel visual guidance system based on virtual driving according to claim 5, characterized in that, The step of calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes: When the evaluation indicators are road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and mitigation of the black hole effect, stable virtual driving is performed based on the speed limit range of the real tunnel corresponding to the virtual tunnel, using the upper limit of the speed limit range. In the digital twin scenario, experiments were conducted on the effectiveness of road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and mitigation of the black-and-white hole effect. In the digital twin scenario, road marking objects, electro-optical sign objects, reflective sign objects, glare road sections, and black-and-white hole effect mitigation road sections are generated respectively. The evaluation results of single-time road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and black-and-white hole effect mitigation are determined based on driver scores. The average value of the evaluation results of the single road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and black-and-white hole effect mitigation under different experimental conditions is taken as the evaluation result of the road marking recognition, electro-optical sign recognition, reflective sign recognition, glare, and black-and-white hole effect mitigation.

7. The evaluation method for a tunnel visual guidance system based on virtual driving according to claim 5, characterized in that, The step of calculating the evaluation index results during the virtual tunnel driving process according to the evaluation index system includes: When the evaluation index is the effectiveness of traffic guidance, stable virtual driving is performed based on the speed limit range of the real tunnel corresponding to the virtual tunnel, using the upper speed limit within the speed limit range. In the digital twin scenario, traffic guidance facilities, including at least variable information signs, variable speed limit signs, delineators, lane indicators, traffic lights, and dynamic guide signs, are randomly generated; the effectiveness evaluation index results for a single traffic guidance session are determined based on driver ratings. The mean of the single traffic guidance effectiveness evaluation index results output under different experimental conditions is taken as the traffic guidance effectiveness evaluation index result.

Images